Parsa-29/loop-config / skills/linear-agent-workflow
linear-agent-workflow
VerifiedUse when coding from Linear issues, syncing task status, creating implementation plans, posting progress comments, or linking GitHub PRs.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 2.3 KB |
SKILL.md
View on GitHub---
name: linear-agent-workflow
description: Use when coding from Linear issues, syncing task status, creating implementation plans, posting progress comments, or linking GitHub PRs.
---
# Linear Agent Workflow
Use Linear as the task context and status surface for coding work.
## When to Use
Use this skill when the user:
- Provides a Linear issue ID or project name.
- Asks what to work on next.
- Asks to sync task status, post progress, or link a GitHub PR.
- Mentions Linear-backed coding, agent task management, worktrees, branches, forks, or PR handoff.
## Workflow
1. Fetch Linear context first.
- Read the issue or project before inspecting code when the task starts from Linear.
- Treat title, description, comments, labels, status, linked PRs, assignee, priority, cycle, and project as task context.
2. Plan before non-trivial work.
- For multi-file, risky, or ambiguous changes, post a short implementation plan as a Linear comment.
- Include intended files/modules, verification commands, risks, and blockers.
3. Keep status aligned.
- Move to `In Progress` when implementation starts.
- Move to `In Review` when a PR exists or the diff is review-ready.
- Move to `Blocked` when credentials, approvals, CI, environment, or product decisions are missing.
4. Report completion in Linear.
- Comment with summary, changed files, verification output, unresolved risks, and PR link if available.
- Do not mark complete unless the requested done condition is satisfied.
## Guardrails
- Do not create or update Linear issues unless the user asked or provided an issue ID.
- Do not invent issue IDs, team names, labels, projects, statuses, or PR URLs.
- Read before write: list/fetch Linear entities before mutating them.
- If Linear tools are unavailable or auth fails, tell the user exactly what failed and continue with local work only if the task has enough context.
- Git push, deploys, DB writes/migrations, dependency additions, secret edits, and live external mutations still require human approval.
## Suggested Linear Comment Shapes
Plan comment:
```md
Plan:
- Scope: ...
- Files/modules: ...
- Verification: ...
- Risks/blockers: ...
```
Completion comment:
```md
Done:
- Summary: ...
- Changed files: ...
- Verification: ...
- PR: ...
- Remaining risks: ...
```
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 471k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |